Spaces:
Sleeping
Sleeping
| <html> | |
| <head> | |
| <script src="http://www.google.com/jsapi" type="text/javascript"></script> | |
| <script type="text/javascript">google.load("jquery", "1.3.2");</script> | |
| <!-- <link rel="stylesheet" href="./static/css/bulma.min.css"> --> | |
| <link rel="stylesheet" href="./static/css/bulma-carousel.min.css"> | |
| <link rel="stylesheet" href="./static/css/bulma-slider.min.css"> | |
| <!-- <link rel="stylesheet" href="./static/css/fontawesome.all.min.css"> --> | |
| <!-- <link rel="stylesheet" | |
| href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css"> --> | |
| <link rel="stylesheet" href="./static/css/index.css"> | |
| <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script> | |
| <script defer src="./static/js/fontawesome.all.min.js"></script> | |
| <script src="./static/js/bulma-carousel.min.js"></script> | |
| <script src="./static/js/bulma-slider.min.js"></script> | |
| <script src="./static/js/index.js"></script> | |
| <script>(function (d, s, id) { | |
| var js, fjs = d.getElementsByTagName(s)[0]; | |
| if (d.getElementById(id)) return; | |
| js = d.createElement(s); js.id = id; | |
| js.src = "https://connect.facebook.net/en_US/sdk.js#xfbml=1&version=v3.0"; | |
| fjs.parentNode.insertBefore(js, fjs); | |
| }(document, 'script', 'facebook-jssdk'));</script> | |
| <script>window.twttr = (function (d, s, id) { | |
| var js, fjs = d.getElementsByTagName(s)[0], | |
| t = window.twttr || {}; | |
| if (d.getElementById(id)) return t; | |
| js = d.createElement(s); | |
| js.id = id; | |
| js.src = "https://platform.twitter.com/widgets.js"; | |
| fjs.parentNode.insertBefore(js, fjs); | |
| t._e = []; | |
| t.ready = function (f) { | |
| t._e.push(f); | |
| }; | |
| return t; | |
| }(document, "script", "twitter-wjs"));</script> | |
| <style type="text/css"> | |
| body { | |
| font-family: "HelveticaNeue-Light", "Helvetica Neue Light", "Helvetica Neue", Helvetica, Arial, "Lucida Grande", sans-serif; | |
| font-weight: 300; | |
| font-size: 18px; | |
| margin-left: auto; | |
| margin-right: auto; | |
| width: 1100px; | |
| } | |
| h1 { | |
| font-size: 32px; | |
| font-weight: 300; | |
| } | |
| .disclaimerbox { | |
| background-color: #eee; | |
| border: 1px solid #eeeeee; | |
| border-radius: 10px; | |
| -moz-border-radius: 10px; | |
| -webkit-border-radius: 10px; | |
| padding: 20px; | |
| } | |
| video.header-vid { | |
| height: 140px; | |
| border: 1px solid black; | |
| border-radius: 10px; | |
| -moz-border-radius: 10px; | |
| -webkit-border-radius: 10px; | |
| } | |
| img.header-img { | |
| height: 140px; | |
| border: 1px solid black; | |
| border-radius: 10px; | |
| -moz-border-radius: 10px; | |
| -webkit-border-radius: 10px; | |
| } | |
| img.rounded { | |
| border: 1px solid #eeeeee; | |
| border-radius: 10px; | |
| -moz-border-radius: 10px; | |
| -webkit-border-radius: 10px; | |
| } | |
| a:link, | |
| a:visited { | |
| color: #1367a7; | |
| text-decoration: none; | |
| } | |
| a:hover { | |
| color: #208799; | |
| } | |
| td.dl-link { | |
| height: 160px; | |
| text-align: center; | |
| font-size: 22px; | |
| } | |
| code { | |
| display: block; | |
| white-space: pre-wrap font-family: Consolas, "courier new"; | |
| color: crimson; | |
| background-color: #f1f1f1; | |
| padding: 2px; | |
| font-size: 105%; | |
| } | |
| pre { | |
| font-family: monospace; | |
| } | |
| .layered-paper-big { | |
| /* modified from: http://css-tricks.com/snippets/css/layered-paper/ */ | |
| box-shadow: | |
| 0px 0px 1px 1px rgba(0, 0, 0, 0.35), | |
| /* The top layer shadow */ | |
| 5px 5px 0 0px #fff, | |
| /* The second layer */ | |
| 5px 5px 1px 1px rgba(0, 0, 0, 0.35), | |
| /* The second layer shadow */ | |
| 10px 10px 0 0px #fff, | |
| /* The third layer */ | |
| 10px 10px 1px 1px rgba(0, 0, 0, 0.35), | |
| /* The third layer shadow */ | |
| 15px 15px 0 0px #fff, | |
| /* The fourth layer */ | |
| 15px 15px 1px 1px rgba(0, 0, 0, 0.35), | |
| /* The fourth layer shadow */ | |
| 20px 20px 0 0px #fff, | |
| /* The fifth layer */ | |
| 20px 20px 1px 1px rgba(0, 0, 0, 0.35), | |
| /* The fifth layer shadow */ | |
| 25px 25px 0 0px #fff, | |
| /* The fifth layer */ | |
| 25px 25px 1px 1px rgba(0, 0, 0, 0.35); | |
| /* The fifth layer shadow */ | |
| margin-left: 10px; | |
| margin-right: 45px; | |
| } | |
| .paper-big { | |
| /* modified from: http://css-tricks.com/snippets/css/layered-paper/ */ | |
| box-shadow: | |
| 0px 0px 1px 1px rgba(0, 0, 0, 0.35); | |
| /* The top layer shadow */ | |
| margin-left: 10px; | |
| margin-right: 45px; | |
| } | |
| .layered-paper { | |
| /* modified from: http://css-tricks.com/snippets/css/layered-paper/ */ | |
| box-shadow: | |
| 0px 0px 1px 1px rgba(0, 0, 0, 0.35), | |
| /* The top layer shadow */ | |
| 5px 5px 0 0px #fff, | |
| /* The second layer */ | |
| 5px 5px 1px 1px rgba(0, 0, 0, 0.35), | |
| /* The second layer shadow */ | |
| 10px 10px 0 0px #fff, | |
| /* The third layer */ | |
| 10px 10px 1px 1px rgba(0, 0, 0, 0.35); | |
| /* The third layer shadow */ | |
| margin-top: 5px; | |
| margin-left: 10px; | |
| margin-right: 30px; | |
| margin-bottom: 5px; | |
| } | |
| .vert-cent { | |
| position: relative; | |
| top: 50%; | |
| transform: translateY(-50%); | |
| } | |
| hr { | |
| border: 0; | |
| height: 1px; | |
| background-image: linear-gradient(to right, rgba(0, 0, 0, 0), rgba(0, 0, 0, 0.75), rgba(0, 0, 0, 0)); | |
| } | |
| </style> | |
| <html> | |
| <head> | |
| <title>TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation | |
| </title> | |
| <meta property="og:image" content="./images/paper.png" /> | |
| <!-- Facebook automatically scrapes this. Go to https://developers.facebook.com/tools/debug/ if you update and want to force Facebook to rescrape. --> | |
| <meta property="og:title" | |
| content="TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation" /> | |
| <meta property="og:description" | |
| content="TIGER is a lightweight model for speech separation which effectively extracts key acoustic features through frequency band-split, multi-scale and full-frequency-frame modeling." /> | |
| <script async src=""></script> | |
| <script> | |
| window.dataLayer = window.dataLayer || []; | |
| function gtag() { dataLayer.push(arguments); } | |
| gtag('js', new Date()); | |
| gtag('config', 'UA-75863369-6'); | |
| </script> | |
| <link rel="icon" type="image/png" | |
| href="https://cdn2.iconfinder.com/data/icons/ios-14-custom-application/62/application-38-512.png" /> | |
| <script async defer src="https://buttons.github.io/buttons.js"></script> | |
| </head> | |
| <body> | |
| <script type="text/javascript" src="script.js"></script> | |
| <br> | |
| <center> | |
| <!-- <img class="round" style="width:500px" src="./images/CPM/cvpr.jpg"/> --> | |
| <!-- <br/> --> | |
| <!-- <br/> --> | |
| <!-- <hr> --> | |
| <span style="font-size:36px">TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient | |
| Speech Separation</span> | |
| <br> | |
| <!-- <hr> --> | |
| <!-- </br> --> | |
| <!-- <span style="font-size:22px; color:#011B56;">━ <a href="https://openaccess.thecvf.com/CVPR2021">CVPR 2021</a> ━</span> --> | |
| <!-- <br></br> --> | |
| <span style="font-size:20px; color:#011B56;">━ <a href="https://openreview.net/pdf?id=rzx3vcvlzj">ICLR 2025</a> ━</span> | |
| <br> | |
| <table align=center width=750px> | |
| <table align=center width=475px> | |
| <tr> | |
| <td align=center width=150px> | |
| <center> | |
| <span style="font-size:22px">Mohan Xu*</span> | |
| </center> | |
| </td> | |
| <td align=center width=150px> | |
| <center> | |
| <span style="font-size:22px"><a href="https://cslikai.cn">Kai Li*</a></span> | |
| </center> | |
| </td> | |
| <td align=center width=150px> | |
| <center> | |
| <span style="font-size:22px">Guo Chen</span> | |
| </center> | |
| </td> | |
| <td align=center width=150px> | |
| <center> | |
| <span style="font-size:22px">Xiaolin Hu</span> | |
| </center> | |
| </td> | |
| </tr> | |
| </table> | |
| <table align=center width=700px> | |
| <tr> | |
| <td align=center> | |
| <center> | |
| <span style="font-size:20px"><a href="https://www.cs.tsinghua.edu.cn/">Tsinghua | |
| University</a> | |
| <!-- <img class="img" width=100px src="./images/vinai-logo.png"></img> --> | |
| </span><br> | |
| <span style="font-size:15px">These authors contributed equally</span> | |
| <!-- <img class="img" width=100px src="./images/vinai-logo.png"></img> --> | |
| </center> | |
| </td> | |
| </tr> | |
| </table> | |
| <table align=center width=600px> | |
| <tr> | |
| <td align=center width=120px> | |
| <center> | |
| <span style="font-size:22px"><a href='https://arxiv.org/abs/2410.01469'>[arXiv | |
| 📝]</a></span> | |
| </center> | |
| </td> | |
| <td align=center width=120px> | |
| <center> | |
| <span style="font-size:22px"><a href='https://github.com/JusperLee/TIGER'>[code | |
| ⚙️]</a></span><br> | |
| </center> | |
| </td> | |
| <!-- <td align=center, width=120px> | |
| <center> | |
| <span style="font-size:22px"><a href='#'>[poster 🖼️]</a></span><br> | |
| </center> | |
| </td> --> | |
| <td align=center, width=120px> | |
| <center> | |
| <span style="font-size:22px"><a href='https://huggingface.co/datasets/JusperLee/EchoSet'>[EchoSet | |
| 🖼️]</a></span><br> | |
| </center> | |
| </td> | |
| </tr> | |
| </table> | |
| </table> | |
| </center> | |
| <br> | |
| <center> | |
| <img class="round" style="width:200px" src="./assets/logo.png" /> | |
| <!-- <p style="max-width:750px;">Given an edit specified by users in <a style="color:red;">an example image</a> (e.g., dog pose),<br>Our method can <a style="color:green;"><b>automatically</b> transfer that edit to other test images</a> (e.g., all dog same pose).</p> --> | |
| <p style="max-width:750px;"><a style="color:red;">TIGER</a> is a <a style="color: blue;"> lightweight model </a> | |
| for speech separation which | |
| <a style="color:green;">effectively extracts key acoustic features through frequency band-split, multi-scale | |
| and full-frequency-frame modeling.</a> | |
| </center> | |
| <hr> | |
| <table align=center width=850px> | |
| <center> | |
| <h1>Abstract</h1> | |
| </center> | |
| <tr> | |
| <td style="text-align: justify;"> | |
| In recent years, much speech separation research has focused primarily on improving model performance. | |
| However, for low-latency speech processing systems, computational efficiency is equally critical. | |
| In this paper, we propose a speech separation model with significantly reduced parameter size and | |
| computational cost: | |
| <i>Time-Frequency Interleaved Gain Extraction and Reconstruction Network (TIGER)</i>. | |
| <a style="background-color:LightYellow;color:red">TIGER leverages prior knowledge to divide frequency | |
| bands and applies compression on frequency information. | |
| We employ a multi-scale selective attention (MSA) module to extract contextual features, | |
| while introducing a full-frequency-frame attention (F^3A) module to capture both temporal and | |
| frequency contextual information. </a> | |
| Additionally, to more realistically evaluate the performance of speech separation models in complex | |
| acoustic environments, | |
| we introduce a novel dataset called <i>EchoSet</i>. This dataset includes noise and more realistic | |
| reverberation | |
| (e.g., considering object occlusions and material properties), with speech from two speakers overlapping | |
| at random proportions. | |
| <a style="color:blue;"> Experimental results demonstrated that TIGER significantly outperformed | |
| state-of-the-art (SOTA) model TF-GridNet | |
| on the EchoSet dataset in both inference speed and separation quality, while reducing the number of | |
| parameters by <b>94.3</b>% | |
| and the MACs by <b>95.3</b>%. </a>These results indicate that by utilizing frequency band-split and | |
| interleaved modeling structures, | |
| TIGER achieves a substantial reduction in parameters and computational costs while maintaining high | |
| performance. | |
| Notably, TIGER is the first speech separation model with fewer than <b>1 million parameters</b> | |
| that achieves performance close to the SOTA model. | |
| </td> | |
| </tr> | |
| </table> | |
| <br> | |
| <center> | |
| <table align=center width=850px> | |
| <tr> | |
| <td width=260px> | |
| <center> | |
| <img class="round" style="width:1000px" src="./assets/TIGER.png" /> | |
| </center> | |
| </td> | |
| </tr> | |
| </table> | |
| <table align=center width=850px> | |
| <tr> | |
| <td> | |
| <center> | |
| Overall pipeline of the model architecture of <a style="color:rgb(255, 136, 0);">TIGER</a> and | |
| its | |
| <a style="color:rgb(187, 0, 255);">modules</a>. | |
| </center> | |
| </td> | |
| </tr> | |
| </table> | |
| </center> | |
| <hr> | |
| <center> | |
| <h1>Results on Speech Separation</h1> | |
| </center> | |
| <center> | |
| <p><img class="round" style='width: 1000px' src='./assets/result.png'> | |
| <figcaption> | |
| <a style="color: hotpink;">Performance comparisons</a> of TIGER and other existing separation models on <a | |
| style="color: orange;">Libri2Mix, LRS2-2Mix, and EchoSet</a>. | |
| Bold indicates optimal performance, and italics indicate suboptimal performance. | |
| </figcaption> | |
| </center> | |
| <center> | |
| <p><img class="round" style='width: 1000px' src='./assets/efficiency.png'> | |
| <figcaption> | |
| <a style="color: hotpink;">Efficiency</a> comparisons of TIGER and other models. | |
| </figcaption> | |
| </center> | |
| <hr> | |
| <center> | |
| <h1>Results on Cinematic Sound Separation</h1> | |
| </center> | |
| <center> | |
| <p><img class="round" style='width: 1000px' src='./assets/dnr.png'> | |
| <figcaption>Comparison of <a style="color: hotpink;">performance and efficiency</a> of cinematic sound | |
| separation models on <a style="color: orange;">DnR</a>. | |
| ‘*’ means the result comes from the original paper of DnR. | |
| </figcaption> | |
| </center> | |
| <hr> | |
| <center> | |
| <h1>Speech Separation Demo</h1> | |
| </center> | |
| <center> | |
| <h3 style="font-weight: bold; color: #ECAEA7">EchoSet Sample I</h3> | |
| <table class="table table-hover pt-2"> | |
| <thread> | |
| <tr> | |
| <th style="text-align: center">Mixture</th> | |
| </tr> | |
| </thread> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample1/GroundTruth/mix.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio> | |
| </td> | |
| </tr> | |
| </table> | |
| <table class="table table-hover pt-2"> | |
| <thead> | |
| <tr> | |
| <th style="text-align: center">Ground Truth</th> | |
| <th style="text-align: center">TF-GridNet</th> | |
| <th style="text-align: center">TIGER</th> | |
| </tr> | |
| </thead> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample1/GroundTruth/s2.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample1/spec/ground_truth_s1.png"> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample1/TFGNet/s1.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample1/spec/TFGNet_s1.png"></td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample1/TIGER/s1.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample1/spec/TIGER_s1.png"></td> | |
| </tr> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample1/GroundTruth/s1.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample1/spec/ground_truth_s2.png"> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample1/TFGNet/s2.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample1/spec/TFGNet_s2.png"></td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample1/TIGER/s2.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample1/spec/TIGER_s2.png"></td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </center> | |
| <center> | |
| <h3 style="font-weight: bold; color: #ECAEA7">EchoSet Sample II</h3> | |
| <table class="table table-hover pt-2"> | |
| <thread> | |
| <tr> | |
| <th style="text-align: center">Mixture</th> | |
| </tr> | |
| </thread> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample2/GroundTruth/mix.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio> | |
| </td> | |
| </tr> | |
| </table> | |
| <table class="table table-hover pt-2"> | |
| <thead> | |
| <tr> | |
| <th style="text-align: center">Ground Truth</th> | |
| <th style="text-align: center">TF-GridNet</th> | |
| <th style="text-align: center">TIGER</th> | |
| </tr> | |
| </thead> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample2/GroundTruth/s2.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample2/spec/ground_truth_s1.png"> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample2/TFGNet/s2.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample2/spec/TFGNet_s1.png"></td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample2/TIGER/s1.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample2/spec/TIGER_s1.png"></td> | |
| </tr> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample2/GroundTruth/s1.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample2/spec/ground_truth_s2.png"> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample2/TFGNet/s1.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample2/spec/TFGNet_s2.png"></td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample2/TIGER/s2.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample2/spec/TIGER_s2.png"></td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </center> | |
| <center> | |
| <h3 style="font-weight: bold; color: #ECAEA7">EchoSet Sample III</h3> | |
| <table class="table table-hover pt-2"> | |
| <thread> | |
| <tr> | |
| <th style="text-align: center">Mixture</th> | |
| </tr> | |
| </thread> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample3/GroundTruth/mix.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio> | |
| </td> | |
| </tr> | |
| </table> | |
| <table class="table table-hover pt-2"> | |
| <thead> | |
| <tr> | |
| <th style="text-align: center">Ground Truth</th> | |
| <th style="text-align: center">TF-GridNet</th> | |
| <th style="text-align: center">TIGER</th> | |
| </tr> | |
| </thead> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample3/GroundTruth/s2.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample3/spec/ground_truth_s1.png"> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample3/TFGNet/s1.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample3/spec/TFGNet_s1.png"></td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample3/TIGER/s1.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample3/spec/TIGER_s1.png"></td> | |
| </tr> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample3/GroundTruth/s1.wav" autoplay="">Your browser does | |
| not support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample3/spec/ground_truth_s2.png"> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample3/TFGNet/s2.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample3/spec/TFGNet_s2.png"></td> | |
| <td style="text-align: center;vertical-align:middle;width: 800px"><audio controls="controls" | |
| style="width: 100%;"> | |
| <source src="assets/sample3/TIGER/s2.wav" autoplay="">Your browser does not | |
| support the audio element. | |
| </audio><img controls="" class="rounded" style="width: 100%;" | |
| src="assets/sample3/spec/TIGER_s2.png"></td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </center> | |
| <hr> | |
| <center> | |
| <h1>Cinematic Sound Demo</h1> | |
| </center> | |
| <center> | |
| <table class="table table-hover pt-2"> | |
| <thread> | |
| <tr> | |
| <th style="text-align: center">Deadpool</th> | |
| </tr> | |
| </thread> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample1/mixture.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| </tr> | |
| </table> | |
| <table class="table table-hover pt-2"> | |
| <thead> | |
| <tr> | |
| <th style="text-align: center">Dialog</th> | |
| <th style="text-align: center">Music</th> | |
| <th style="text-align: center">Effect</th> | |
| </tr> | |
| </thead> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample1/dialog.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample1/music.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample1/effect.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </center> | |
| <center> | |
| <table class="table table-hover pt-2"> | |
| <thread> | |
| <tr> | |
| <th style="text-align: center">The Wandering Earth</th> | |
| </tr> | |
| </thread> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample2/mixture.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| </tr> | |
| </table> | |
| <table class="table table-hover pt-2"> | |
| <thead> | |
| <tr> | |
| <th style="text-align: center">Dialog</th> | |
| <th style="text-align: center">Music</th> | |
| <th style="text-align: center">Effect</th> | |
| </tr> | |
| </thead> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample2/dialog.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample2/music.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample2/effect.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </center> | |
| <center> | |
| <table class="table table-hover pt-2"> | |
| <thread> | |
| <tr> | |
| <th style="text-align: center">Captain America</th> | |
| </tr> | |
| </thread> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample3/mixture.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| </tr> | |
| </table> | |
| <table class="table table-hover pt-2"> | |
| <thead> | |
| <tr> | |
| <th style="text-align: center">Dialog</th> | |
| <th style="text-align: center">Music</th> | |
| <th style="text-align: center">Effect</th> | |
| </tr> | |
| </thead> | |
| <tbody> | |
| <tr> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample3/dialog.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample3/music.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| <td style="text-align: center;vertical-align:middle;width: 365px"> | |
| <video controls style="width: 100%;"> | |
| <source src="assets/dnr-demo/sample3/effect.mp4" type="video/mp4"> | |
| </video> | |
| </td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </center> | |
| <hr> | |
| <table align=center width=900px> | |
| <tr> | |
| <td width=400px> | |
| <left> | |
| <center> | |
| <h1>Acknowledgements</h1> | |
| </center> | |
| Website template was borrowed from <a href="http://richzhang.github.io/colorization/">Colorful Image | |
| Colorization</a> and <a href="https://nerfies.github.io/">Nerfies</a>; the code can be found <a | |
| href="https://github.com/richzhang/webpage-template">here</a> and <a | |
| href="https://github.com/nerfies/nerfies.github.io">here</a>. Thank you (.❛ ᴗ ❛.). | |
| </left> | |
| </td> | |
| </tr> | |
| </table> | |
| <center> | |
| <a href="javascript:toggleblock('notice')" style="text-align:center;font-size:70%;color:#808080">▶ cslikai.cn's | |
| clustrmaps 🌎</a>. | |
| <div id="notice" style="display:none; color:#dedede; font-size:.5em;"> | |
| <p> | |
| <script type="text/javascript" id="clustrmaps" src="//clustrmaps.com/map_v2.js?d=XUY5Bbv-l4Negr0uiIqE4axKMGnlqBRBDKL5EpeE2LY&cl=ffffff&w=a"></script> | |
| </p> | |
| </div> | |
| </center> | |
| <br> | |
| </body> | |
| </html> |